Security Audit

graphhopper-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

graphhopper-automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Broad tool execution capability via Rube MCP.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad tool execution capability via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow the execution of arbitrary tools discovered through `RUBE_SEARCH_TOOLS`. The `SKILL.md` does not define or constrain the permissions of these underlying tools. This means the LLM could be instructed to execute tools with excessive permissions (e.g., filesystem access, network access, or other sensitive operations) if such tools are available via Rube MCP. This exposes the LLM to the full scope of permissions granted to the Rube MCP system and its integrated toolkits, potentially leading to unintended actions or data exposure if a malicious prompt is crafted. Implement granular access control for tools available via Rube MCP, ensuring that the LLM can only access tools with the minimum necessary permissions for the Graphhopper domain. If possible, restrict the `tool_slug` values that can be executed by this specific skill, or provide a whitelist of allowed tools. Ensure that `RUBE_SEARCH_TOOLS` only returns tools relevant and necessary for the skill's intended purpose.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/063a4c4ed8b12335.svg)](https://skillshield.io/report/063a4c4ed8b12335)